Skip to main content
Answered

Using Custom Actions as branching criteria

  • April 7, 2025
  • 1 reply
  • 23 views

I am working on new Fin Tasks where I want to create a branches with conditions that are dependent on the results of a custom action. Can anyone help me understand how to build this? For example if a Custom Action returns [X] then follow this path, and if Custom Action returns [Y] follow a different branch

Best answer by Paul B12

Hey ​@Ben_M 

To build branches in a Fin Task based on the result of a Custom Action, you'll first need to create the Custom Action in Settings → Integrations → Actions and map the response (e.g. { "order_status": "order_found" }) to a custom variable.

 

Then, in Fin AI Agent → Train → Tasks, create a task that collects any needed input (like an order ID), runs the Custom Action, and stores the result.

 

Next, go to Automation → Workflows, add a Fin Task step, and create branches based on the value of that variable — for example, if order_status is "order_found", send a success message, and if it's "order_not_found", ask for more info.

Hope that helps :)

View original
Did this topic help you find an answer to your question?

1 reply

Paul Byrne
Intercom Team
Forum|alt.badge.img+2
  • Intercom Team
  • 28 replies
  • Answer
  • April 20, 2025

Hey ​@Ben_M 

To build branches in a Fin Task based on the result of a Custom Action, you'll first need to create the Custom Action in Settings → Integrations → Actions and map the response (e.g. { "order_status": "order_found" }) to a custom variable.

 

Then, in Fin AI Agent → Train → Tasks, create a task that collects any needed input (like an order ID), runs the Custom Action, and stores the result.

 

Next, go to Automation → Workflows, add a Fin Task step, and create branches based on the value of that variable — for example, if order_status is "order_found", send a success message, and if it's "order_not_found", ask for more info.

Hope that helps :)


Reply


Cookie policy

We use cookies to enhance and personalize your experience. If you accept you agree to our full cookie policy. Learn more about our cookies.

 
Cookie settings